Bayesian Model Averaging under Regime Switching with Application to Cyclical Macro Variable Forecasting

Model uncertainty and recurrent or cyclical structural changes in macroeconomic time series dynamics are substantial challenges to macroeconomic forecasting. This paper discusses a macro variable forecasting methodology that combines model uncertainty and regime switching simultaneously. The proposed predictive regression specification permits both regime switching of the regression parameters and uncertainty about the inclusion of forecasting variables by employing Bayesian model averaging. In an empirical exercise involving quarterly US inflation, we observed that our Bayesian model averaging with regime switching leads to substantial improvements in forecast performance, particularly in the medium horizon (two to four quarters). Copyright © 2015 John Wiley & Sons, Ltd.     

The role of age‐structured education data for economic growth forecasts

This paper utilizes for the first time age‐structured human capital data for economic growth forecasting. We concentrate on pooled cross‐country data of 65 countries over six 5‐year periods (1970–2000) and consider specifications chosen by model selection criteria, Bayesian model averaging methodologies based on in‐sample and out‐of‐sample goodness of fit and on adaptive regression by mixing. The results indicate that forecast averaging and exploiting the demographic dimension of education data improve economic growth forecasts systematically. In particular, the results are very promising for improving economic growth predictions in developing countries. Copyright © 2009 John Wiley & Sons, Ltd.     

Can forecasting performance be improved by considering the steady state? An application to Swedish inflation and interest rate

This paper investigates whether the forecasting performance of Bayesian autoregressive and vector autoregressive models can be improved by incorporating prior beliefs on the steady state of the time series in the system. Traditional methodology is compared to the new framework—in which a mean‐adjusted form of the models is employed—by estimating the models on Swedish inflation and interest rate data from 1980 to 2004. Results show that the out‐of‐sample forecasting ability of the models is practically unchanged for inflation but significantly improved for the interest rate when informative prior distributions on the steady state are provided. The findings in this paper imply that this new methodology could be useful since it allows us to sharpen our forecasts in the presence of potential pitfalls such as near unit root processes and structural breaks, in particular when relying on small samples. Copyright © 2008 John Wiley & Sons, Ltd.     

Forecasting with Specification‐Switching VARs

The specification choices of vector autoregressions (VARs) in forecasting are often not straightforward, as they are complicated by various factors. To deal with model uncertainty and better utilize multiple VARs, this paper adopts the dynamic model averaging/selection (DMA/DMS) algorithm, in which forecasting models are updated and switch over time in a Bayesian manner. In an empirical application to a pool of Bayesian VAR (BVAR) models whose specifications include level and difference, along with differing lag lengths, we demonstrate that specification‐switching VARs are flexible and powerful forecast tools that yield good performance. In particular, they beat the overall best BVAR in most cases and are comparable to or better than the individual best models (for each combination of variable, forecast horizon, and evaluation metrics) for medium‐ and long‐horizon forecasts. We also examine several extensions in which forecast model pools consist of additional individual models in partial differences as well as all level/difference models, and/or time variations in VAR innovations are allowed, and discuss the potential advantages and disadvantages of such specification choices. Copyright © 2016 John Wiley & Sons, Ltd.     

The impact of parameter and model uncertainty on market risk predictions from GARCH‐type models

We study the effect of parameter and model uncertainty on the left‐tail of predictive densities and in particular on VaR forecasts. To this end, we evaluate the predictive performance of several GARCH‐type models estimated via Bayesian and maximum likelihood techniques. In addition to individual models, several combination methods are considered, such as Bayesian model averaging and (censored) optimal pooling for linear, log or beta linear pools. Daily returns for a set of stock market indexes are predicted over about 13 years from the early 2000s. We find that Bayesian predictive densities improve the VaR backtest at the 1% risk level for single models and for linear and log pools. We also find that the robust VaR backtest exhibited by linear and log pools is better than the backtest of single models at the 5% risk level. Finally, the equally weighted linear pool of Bayesian predictives tends to be the best VaR forecaster in a set of 42 forecasting techniques.     

Robust model rankings of forecasting performance

This paper investigates robust model rankings in out‐of‐sample, short‐horizon forecasting. We provide strong evidence that rolling window averaging consistently produces robust model rankings while improving the forecasting performance of both individual models and model averaging. The rolling window averaging outperforms the (ex post) “optimal” window forecasts in more than 50% of the times across all rolling windows.     

A Bayesian structural model for predicting algal blooms

A Bayesian structural model with two components is proposed to forecast the occurrence of algal blooms, multivariate mean‐reverting diffusion process (MMRD), and a binary probit model with latent Markov regime‐switching process (BPMRS). The model has three features: (a) forecast of the occurrence probability of algal bloom is directly based on oceanographic parameters, not the forecasting of special indicators in traditional approaches, such as phytoplankton or chlorophyll‐a; (b) augmentation of daily oceanographic parameters from the data collected every 2 weeks is based on MMRD. The proposed method solves the problem of unavailability of daily oceanographic parameters in practice; (c) BPMRS captures the unobservable factors which affect algal bloom occurrence and therefore improve forecast accuracy. We use panel data collected in Tolo Harbour, Hong Kong, to validate the model. The model demonstrates good forecasting for out‐of‐sample rolling forecasts, especially for algal bloom appearing for a longer period, which severely damages fisheries and the marine environment.     

A classifying procedure for signalling turning points

A Hidden Markov Model (HMM) is used to classify an out‐of‐sample observation vector into either of two regimes. This leads to a procedure for making probability forecasts for changes of regimes in a time series, i.e. for turning points. Instead of estimating past turning points using maximum likelihood, the model is estimated with respect to known past regimes. This makes it possible to perform feature extraction and estimation for different forecasting horizons. The inference aspect is emphasized by including a penalty for a wrong decision in the cost function. The method, here called a ‘Markov Bayesian Classifier (MBC)’, is tested by forecasting turning points in the Swedish and US economies, using leading data. Clear and early turning point signals are obtained, contrasting favourably with earlier HMM studies. Some theoretical arguments for this are given. Copyright © 2004 John Wiley & Sons, Ltd.     

Space‐Time Model versus VAR Model: Forecasting Electricity demand in Japan

This paper examined the forecasting performance of disaggregated data with spatial dependency and applied it to forecasting electricity demand in Japan. We compared the performance of the spatial autoregressive ARMA (SAR‐ARMA) model with that of the vector autoregressive (VAR) model from a Bayesian perspective. With regard to the log marginal likelihood and log predictive density, the VAR(1) model performed better than the SAR‐ARMA( 1,1) model. In the case of electricity demand in Japan, we can conclude that the VAR model with contemporaneous aggregation had better forecasting performance than the SAR‐ARMA model. Copyright © 2011 John Wiley & Sons, Ltd.     

Bayesian forecasts for cointegrated models

This paper investigates Bayesian forecasts for some cointegrated time series data. Suppose data are derived from some cointegrated model, but, an unrestricted vector autoregressive model, without including cointegrated conditions, is fitted; the implication of using an incorrect model will be investigated from the Bayesian forecasting viewpoint. For some special cointegrated data and under the diffuse prior assumption, it can be analytically proven that the posterior predictive distributions for both the true model and the fitted model are asymptotically the same for any future step. For a more general cointegrated model, examinations are performed via simulations. Some simulated results reveal that a reasonably unrestricted model will still provide a rather accurate forecast as long as the sample size is large enough or the forecasting period is not too far in the future. For a small sample size or for long‐term forecasting, more accurate forecasts are expected if the correct cointegrated model is actually applied. Copyright © 2002 John Wiley & Sons, Ltd.     

Volatility forecasting with double Markov switching GARCH models

This paper investigates inference and volatility forecasting using a Markov switching heteroscedastic model with a fat‐tailed error distribution to analyze asymmetric effects on both the conditional mean and conditional volatility of financial time series. The motivation for extending the Markov switching GARCH model, previously developed to capture mean asymmetry, is that the switching variable, assumed to be a first‐order Markov process, is unobserved. The proposed model extends this work to incorporate Markov switching in the mean and variance simultaneously. Parameter estimation and inference are performed in a Bayesian framework via a Markov chain Monte Carlo scheme. We compare competing models using Bayesian forecasting in a comparative value‐at‐risk study. The proposed methods are illustrated using both simulations and eight international stock market return series. The results generally favor the proposed double Markov switching GARCH model with an exogenous variable. Copyright © 2008 John Wiley & Sons, Ltd.     

A New‐Keynesian DSGE model for forecasting the South African economy

This paper develops a New‐Keynesian Dynamic Stochastic General Equilibrium (NKDSGE) model for forecasting the growth rate of output, inflation, and the nominal short‐term interest rate (91 days Treasury Bill rate) for the South African economy. The model is estimated via maximum likelihood technique for quarterly data over the period of 1970:1–2000:4. Based on a recursive estimation using the Kalman filter algorithm, out‐of‐sample forecasts from the NKDSGE model are compared with forecasts generated from the classical and Bayesian variants of vector autoregression (VAR) models for the period 2001:1–2006:4. The results indicate that in terms of out‐of‐sample forecasting, the NKDSGE model outperforms both the classical and Bayesian VARs for inflation, but not for output growth and nominal short‐term interest rate. However, differences in RMSEs are not significant across the models. Copyright © 2008 John Wiley & Sons, Ltd.     

Forecasting US inflation by Bayesian model averaging

Recent empirical work has considered the prediction of inflation by combining the information in a large number of time series. One such method that has been found to give consistently good results consists of simple equal‐weighted averaging of the forecasts from a large number of different models, each of which is a linear regression relating inflation to a single predictor and a lagged dependent variable. In this paper, I consider using Bayesian model averaging for pseudo out‐of‐sample prediction of US inflation, and find that it generally gives more accurate forecasts than simple equal‐weighted averaging. This superior performance is consistent across subsamples and a number of inflation measures. Copyright © 2008 John Wiley & Sons, Ltd.     

Model uncertainty and forecast accuracy

In time-series analysis, a model is rarely pre-specified but rather is typically formulated in an iterative, interactive way using the given time-series data. Unfortunately the properties of the fitted model, and the forecasts from it, are generally calculated as if the model were known in the first place. This is theoretically incorrect, as least squares theory, for example, does not apply when the same data are used to formulates and fit a model. Ignoring prior model selection leads to biases, not only in estimates of model parameters but also in the subsequent construction of prediction intervals. The latter are typically too narrow, partly because they do not allow for model uncertainty. Empirical results also suggest that more complicated models tend to give a better fit but poorer ex-ante forecasts. The reasons behind these phenomena are reviewed. When comparing different forecasting models, the BIC is preferred to the AIC for identifying a model on the basis of within-sample fit, but out-of-sample forecasting accuracy provides the real test. Alternative approaches to forecasting, which avoid conditioning on a single model, include Bayesian model averaging and using a forecasting method which is not model-based but which is designed to be adaptable and robust.     

Quantile Double AR Time Series Models for Financial Returns

We develop a novel quantile double autoregressive model for modelling financial time series. This is done by specifying a generalized lambda distribution to the quantile function of the location‐scale double autoregressive model developed by Ling (2004, 2007). Parameter estimation uses Markov chain Monte Carlo Bayesian methods. A simulation technique is introduced for forecasting the conditional distribution of financial returns m periods ahead, and hence any for predictive quantities of interest. The application to forecasting value‐at‐risk at different time horizons and coverage probabilities for Dow Jones Industrial Average shows that our method works very well in practice. Copyright © 2013 John Wiley & Sons, Ltd.     

Beating the random walk in Central and Eastern Europe

We compare the accuracy of vector autoregressive (VAR), restricted vector autoregressive (RVAR), Bayesian vector autoregressive (BVAR), vector error correction (VEC) and Bayesian error correction (BVEC) models in forecasting the exchange rates of five Central and Eastern European currencies (Czech Koruna, Hungarian Forint, Slovak Koruna, Slovenian Tolar and Polish Zloty) against the US Dollar and the Euro. Although these models tend to outperform the random walk model for long‐term predictions (6 months ahead and beyond), even the best models in terms of average prediction error fail to reject the test of equality of forecasting accuracy against the random walk model in short‐term predictions. Copyright © 2005 John Wiley & Sons, Ltd.     

On forecasting counts

Forecasting for a time series of low counts, such as forecasting the number of patents to be awarded to an industry, is an important research topic in socio‐economic sectors. Recently (2004), Freeland and McCabe introduced a Gaussian type stationary correlation model‐based forecasting which appears to work well for the stationary time series of low counts. In practice, however, it may happen that the time series of counts will be non‐stationary and also the series may contain over‐dispersed counts. To develop the forecasting functions for this type of non‐stationary over‐dispersed data, the paper provides an extension of the stationary correlation models for Poisson counts to the non‐stationary correlation models for negative binomial counts. The forecasting methodology appears to work well, for example, for a US time series of polio counts, whereas the existing Bayesian methods of forecasting appear to encounter serious convergence problems. Further, a simulation study is conducted to examine the performance of the proposed forecasting functions, which appear to work well irrespective of whether the time series contains small or large counts. Copyright © 2008 John Wiley & Sons, Ltd.     

Improving moving average trading rules with boosting and statistical learning methods

We present a system for combining the different types of predictions given by a wide category of mechanical trading rules through statistical learning methods (boosting, and several model averaging methods like Bayesian or simple averaging methods). Statistical learning methods supply better out‐of‐sample results than most of the single moving average rules in the NYSE Composite Index from January 1993 to December 2002. Moreover, using a filter to reduce trading frequency, the filtered boosting model produces a technical strategy which, although it is not able to overcome the returns of the buy‐and‐hold (B&H) strategy during rising periods, it does overcome the B&H during falling periods and is able to absorb a considerable part of falls in the market. Copyright © 2008 John Wiley & Sons, Ltd.     

Adaptive learning from model space

Dynamic model averaging (DMA) is used extensively for the purpose of economic forecasting. This study extends the framework of DMA by introducing adaptive learning from model space. In the conventional DMA framework all models are estimated independently and hence the information of the other models is left unexploited. In order to exploit the information in the estimation of the individual time‐varying parameter models, this paper proposes not only to average over the forecasts but, in addition, also to dynamically average over the time‐varying parameters. This is done by approximating the mixture of individual posteriors with a single posterior, which is then used in the upcoming period as the prior for each of the individual models. The relevance of this extension is illustrated in three empirical examples involving forecasting US inflation, US consumption expenditures, and forecasting of five major US exchange rate returns. In all applications adaptive learning from model space delivers improvements in out‐of‐sample forecasting performance.     

Modeling and forecasting aggregate stock market volatility in unstable environments using mixture innovation regressions

We perform Bayesian model averaging across different regressions selected from a set of predictors that includes lags of realized volatility, financial and macroeconomic variables. In our model average, we entertain different channels of instability by either incorporating breaks in the regression coefficients of each individual model within our model average, breaks in the conditional error variance, or both. Changes in these parameters are driven by mixture distributions for state innovations (MIA) of linear Gaussian state‐space models. This framework allows us to compare models that assume small and frequent as well as models that assume large but rare changes in the conditional mean and variance parameters. Results using S&P 500 monthly and quarterly realized volatility data from 1960 to 2014 suggest that Bayesian model averaging in combination with breaks in the regression coefficients and the error variance through MIA dynamics generates statistically significantly more accurate forecasts than the benchmark autoregressive model. However, compared to a MIA autoregression with breaks in the regression coefficients and the error variance, we fail to provide any drastic improvements.